{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OMLE4V37ONR5TGZLHHAEJVBR4Q","short_pith_number":"pith:OMLE4V37","canonical_record":{"source":{"id":"2508.07713","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-11T07:39:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d2589f1431e01579f474c7f43984ff7130dcc2eec1ec74e460f792f815fe61bb","abstract_canon_sha256":"c6169372f7ebc47219e25fdb147f02cda63249705e9f064d3c9610f56267a387"},"schema_version":"1.0"},"canonical_sha256":"73164e577f7363d99b2b39c044d431e4296d72dbdd2e0916e344ac106e2820f8","source":{"kind":"arxiv","id":"2508.07713","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07713","created_at":"2026-07-05T11:51:50Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07713v1","created_at":"2026-07-05T11:51:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07713","created_at":"2026-07-05T11:51:50Z"},{"alias_kind":"pith_short_12","alias_value":"OMLE4V37ONR5","created_at":"2026-07-05T11:51:50Z"},{"alias_kind":"pith_short_16","alias_value":"OMLE4V37ONR5TGZL","created_at":"2026-07-05T11:51:50Z"},{"alias_kind":"pith_short_8","alias_value":"OMLE4V37","created_at":"2026-07-05T11:51:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OMLE4V37ONR5TGZLHHAEJVBR4Q","target":"record","payload":{"canonical_record":{"source":{"id":"2508.07713","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-11T07:39:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d2589f1431e01579f474c7f43984ff7130dcc2eec1ec74e460f792f815fe61bb","abstract_canon_sha256":"c6169372f7ebc47219e25fdb147f02cda63249705e9f064d3c9610f56267a387"},"schema_version":"1.0"},"canonical_sha256":"73164e577f7363d99b2b39c044d431e4296d72dbdd2e0916e344ac106e2820f8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:50.989851Z","signature_b64":"SDZDHlQ6V/YsxXhW1+Ay3RFpv0/g+MKGguVigZZ7LqFxMlXDucf3rrfysyWYX7+xzyWC/vQ3A/9SOknHq+K+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73164e577f7363d99b2b39c044d431e4296d72dbdd2e0916e344ac106e2820f8","last_reissued_at":"2026-07-05T11:51:50.989396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:50.989396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.07713","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:51:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lfi0Z0WElOQCGR9utjJzzy+3pwDexryY4k/cwYnFNcl0DUUfwFp9T8u4TUA46u3Wwp+kwcT1FlRltyd0z0ftDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:44:23.859081Z"},"content_sha256":"8e1ad82242f8aef44ccbf00a11fc6bf291642c53b29f4d1a66705e8ae7555d80","schema_version":"1.0","event_id":"sha256:8e1ad82242f8aef44ccbf00a11fc6bf291642c53b29f4d1a66705e8ae7555d80"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OMLE4V37ONR5TGZLHHAEJVBR4Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Detecting Mislabeled and Corrupted Data via Pointwise Mutual Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiayu Weng, Jinghan Yang","submitted_at":"2025-08-11T07:39:20Z","abstract_excerpt":"Deep neural networks can memorize corrupted labels, making data quality critical for model performance, yet real-world datasets are frequently compromised by both label noise and input noise. This paper proposes a mutual information-based framework for data selection under hybrid noise scenarios that quantifies statistical dependencies between inputs and labels. We compute each sample's pointwise contribution to the overall mutual information and find that lower contributions indicate noisy or mislabeled instances. Empirical validation on MNIST with different synthetic noise settings demonstra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07713","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.07713/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:51:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OLZR/mRZ6Xip5syiX0uLb4Bft9mvxzqSdHBxu/jod/NB32F3Uk0xnOITtNYBbXldFOdxt1b6LIPdagIzmxzMCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:44:23.859585Z"},"content_sha256":"40583d5df7aa8099350b1b1330379d27622c95279976fa4bc69c74089ab91ee6","schema_version":"1.0","event_id":"sha256:40583d5df7aa8099350b1b1330379d27622c95279976fa4bc69c74089ab91ee6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OMLE4V37ONR5TGZLHHAEJVBR4Q/bundle.json","state_url":"https://pith.science/pith/OMLE4V37ONR5TGZLHHAEJVBR4Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OMLE4V37ONR5TGZLHHAEJVBR4Q/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T10:44:23Z","links":{"resolver":"https://pith.science/pith/OMLE4V37ONR5TGZLHHAEJVBR4Q","bundle":"https://pith.science/pith/OMLE4V37ONR5TGZLHHAEJVBR4Q/bundle.json","state":"https://pith.science/pith/OMLE4V37ONR5TGZLHHAEJVBR4Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OMLE4V37ONR5TGZLHHAEJVBR4Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OMLE4V37ONR5TGZLHHAEJVBR4Q","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c6169372f7ebc47219e25fdb147f02cda63249705e9f064d3c9610f56267a387","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-11T07:39:20Z","title_canon_sha256":"d2589f1431e01579f474c7f43984ff7130dcc2eec1ec74e460f792f815fe61bb"},"schema_version":"1.0","source":{"id":"2508.07713","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07713","created_at":"2026-07-05T11:51:50Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07713v1","created_at":"2026-07-05T11:51:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07713","created_at":"2026-07-05T11:51:50Z"},{"alias_kind":"pith_short_12","alias_value":"OMLE4V37ONR5","created_at":"2026-07-05T11:51:50Z"},{"alias_kind":"pith_short_16","alias_value":"OMLE4V37ONR5TGZL","created_at":"2026-07-05T11:51:50Z"},{"alias_kind":"pith_short_8","alias_value":"OMLE4V37","created_at":"2026-07-05T11:51:50Z"}],"graph_snapshots":[{"event_id":"sha256:40583d5df7aa8099350b1b1330379d27622c95279976fa4bc69c74089ab91ee6","target":"graph","created_at":"2026-07-05T11:51:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.07713/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks can memorize corrupted labels, making data quality critical for model performance, yet real-world datasets are frequently compromised by both label noise and input noise. This paper proposes a mutual information-based framework for data selection under hybrid noise scenarios that quantifies statistical dependencies between inputs and labels. We compute each sample's pointwise contribution to the overall mutual information and find that lower contributions indicate noisy or mislabeled instances. Empirical validation on MNIST with different synthetic noise settings demonstra","authors_text":"Jiayu Weng, Jinghan Yang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-11T07:39:20Z","title":"Detecting Mislabeled and Corrupted Data via Pointwise Mutual Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07713","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8e1ad82242f8aef44ccbf00a11fc6bf291642c53b29f4d1a66705e8ae7555d80","target":"record","created_at":"2026-07-05T11:51:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c6169372f7ebc47219e25fdb147f02cda63249705e9f064d3c9610f56267a387","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-11T07:39:20Z","title_canon_sha256":"d2589f1431e01579f474c7f43984ff7130dcc2eec1ec74e460f792f815fe61bb"},"schema_version":"1.0","source":{"id":"2508.07713","kind":"arxiv","version":1}},"canonical_sha256":"73164e577f7363d99b2b39c044d431e4296d72dbdd2e0916e344ac106e2820f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73164e577f7363d99b2b39c044d431e4296d72dbdd2e0916e344ac106e2820f8","first_computed_at":"2026-07-05T11:51:50.989396Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:50.989396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SDZDHlQ6V/YsxXhW1+Ay3RFpv0/g+MKGguVigZZ7LqFxMlXDucf3rrfysyWYX7+xzyWC/vQ3A/9SOknHq+K+CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:50.989851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.07713","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e1ad82242f8aef44ccbf00a11fc6bf291642c53b29f4d1a66705e8ae7555d80","sha256:40583d5df7aa8099350b1b1330379d27622c95279976fa4bc69c74089ab91ee6"],"state_sha256":"ff9c6f7b11abd45849042141c744f8a8587d81a00d04331250b7c29121a5f8b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jY6Hk8iDiXOF4Qb8Pvwco1BIz0KuWBmoEHzL3kW2Teb7OAkRMQCc1hp9Mrt1Q7xlMYa4Z5UOI/VaKW7hNbdcAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T10:44:23.863477Z","bundle_sha256":"ef785e3d74493945d8f33058216bc81be9997273a0c5ea09c36cc12f9b8417e8"}}